tensorflow(6)——卷积神经网络

学习《Tensorflow入门教程》记录 

卷积神经网络流程框图如下：

First Conv and Pool Layers ——Second Conv and Pool Layers——First Fully Connected Layer——Dropout Layer——Second Fully Connected Layer——Final Layer
池化层简单理解：把卷积得到的结果进行降维处理。

示例代码：

import tensorflow as tf
import random
import numpy as np
import matplotlib.pyplot as plt
import datetime

from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("data/", one_hot=True)

tf.reset_default_graph()
sess = tf.InteractiveSession()
x = tf.placeholder("float", shape = [None, 28,28,1])
y_ = tf.placeholder("float", shape = [None, 10])

#5*5的卷积核  1个通道的输入图像  32个不同的卷积核，得到32个特征图
W_conv1 = tf.Variable(tf.truncated_normal([5, 5, 1, 32], stddev=0.1))
#偏置
b_conv1 = tf.Variable(tf.constant(.1, shape = [32]))

#进行卷积运算
#[1, 1, 1, 1] 中间2个1，卷积每次滑动的步长
#padding='SAME' 边缘自动补充
h_conv1 = tf.nn.conv2d(input=x, filter=W_conv1, strides=[1, 1, 1, 1], padding='SAME') + b_conv1
h_conv1 = tf.nn.relu(h_conv1)
#进行池化
h_pool1 = tf.nn.max_pool(h_conv1, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')

#定义为函数
def conv2d(x, W):
    return tf.nn.conv2d(input=x, filter=W, strides=[1, 1, 1, 1], padding='SAME')

def max_pool_2x2(x):
    return tf.nn.max_pool(x, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')

#全连接层
W_conv2 = tf.Variable(tf.truncated_normal([5, 5, 32, 64], stddev=0.1))
b_conv2 = tf.Variable(tf.constant(.1, shape = [64]))
h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
h_pool2 = max_pool_2x2(h_conv2)

#First Fully Connected Layer
#经过了2次卷积和池化 28*28*1变成了7*7*64  定义得到了1024维特征
W_fc1 = tf.Variable(tf.truncated_normal([7 * 7 * 64, 1024], stddev=0.1))
b_fc1 = tf.Variable(tf.constant(.1, shape = [1024]))
h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])   #把特征拉成1条
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)

#Dropout Layer，防止过拟合
keep_prob = tf.placeholder("float")
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)

#第二次全连接层
W_fc2 = tf.Variable(tf.truncated_normal([1024, 10], stddev=0.1))
b_fc2 = tf.Variable(tf.constant(.1, shape = [10]))

#Final Layer
y = tf.matmul(h_fc1_drop, W_fc2) + b_fc2

crossEntropyLoss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels = y_, logits = y))
trainStep = tf.train.AdamOptimizer().minimize(crossEntropyLoss)
correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))

sess.run(tf.global_variables_initializer())

batchSize = 50
for i in range(1000):
    batch = mnist.train.next_batch(batchSize)
    trainingInputs = batch[0].reshape([batchSize,28,28,1])
    trainingLabels = batch[1]
    if i%100 == 0:
        trainAccuracy = accuracy.eval(session=sess, feed_dict={x:trainingInputs, y_: trainingLabels, keep_prob: 1.0})
        print ("step %d, training accuracy %g"%(i, trainAccuracy))
    trainStep.run(session=sess, feed_dict={x: trainingInputs, y_: trainingLabels, keep_prob: 0.5})

运行结果：
step 0, training accuracy 0.2
step 100, training accuracy 0.84
step 200, training accuracy 1
step 300, training accuracy 0.96
step 400, training accuracy 1
step 500, training accuracy 0.96
step 600, training accuracy 1
step 700, training accuracy 0.96
step 800, training accuracy 0.96
step 900, training accuracy 0.96